Skip to content

Browser Automation for VS Code

io.github.mindstone/mcp-server-browser-automation

Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs

client:VS Code transport:stdio runtime:npm

Install Browser Automation in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "agent-browser-session-name",
      "description": "AGENT_BROWSER_SESSION_NAME",
      "password": true
    },
    {
      "type": "promptString",
      "id": "agent-browser-show-window",
      "description": "AGENT_BROWSER_SHOW_WINDOW",
      "password": true
    },
    {
      "type": "promptString",
      "id": "mcp-workspace-path",
      "description": "MCP_WORKSPACE_PATH",
      "password": true
    }
  ],
  "servers": {
    "mcp-server-browser-automation": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@mindstone/mcp-server-browser-automation"
      ],
      "env": {
        "AGENT_BROWSER_SESSION_NAME": "${input:agent-browser-session-name}",
        "AGENT_BROWSER_SHOW_WINDOW": "${input:agent-browser-show-window}",
        "MCP_WORKSPACE_PATH": "${input:mcp-workspace-path}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

Browser Automation in other clients